INDEX

Explanations

terms related to death and dying

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WEBPACK

-0.86

ništ

-0.84

seguida

-0.78

 autorytatywna

-0.75

GGLE

-0.74

useppe

-0.73

itoire

-0.73

Vea

-0.73

Cym

-0.72

 Fant

-0.71

POSITIVE LOGITS

 death

1.19

 DEATH

1.16

 dies

1.15

 deaths

1.11

 Death

1.10

 died

1.07

 dying

1.07

 Deaths

1.04

death

1.03

Death

1.01

Activations Density 0.094%

terms related to death and dying

No Comments

No Known Activations